INDEX

Explanations

="

np_max-act · gemini-2.0-flash

The neuron primarily fires on HTML `<meta>` tags with `name` attributes (e.g. viewport, description, author).

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<!--[

-0.07

 صرف

-0.06

(Category

-0.06

\Resource

-0.06

'})↵↵

-0.06

_usb

-0.06

歩

-0.06

_consumer

-0.06

�

-0.06

 gourmet

-0.06

POSITIVE LOGITS

 recruiting

0.07

ズ

0.07

 embodiment

0.07

 Navy

0.06

CENT

0.06

vere

0.06

elyn

0.06

='

0.06

 rollout

0.06

iddled

0.06

Activations Density 0.001%

="

The neuron primarily fires on HTML `<meta>` tags with `name` attributes (e.g. viewport, description, author).

No Comments

No Known Activations